In the physiological-based affective computing literature, there is a large number of public datasets available (e.g. Compared to video or text-based emotion recognition, the use of physiological data offers several advantages, including unobtrusive data collection over extended periods for individuals and groups, high spatial and temporal resolution, and reduced susceptibility to conscious manipulation by subjects. This growth has also been observed in emotion recognition based on physiological data, namely through unobtrusive physiological sensors which aim to capture data in real-life settings. In addition to body and facial expressions, emotions can be measured using autonomic nervous system responses. AffectNet 2 with 0.4 million annotated facial expressions EmotiW challenge 3 with 1088 annotated videos), which is crucial for the development of accurate artificial intelligent algorithms. For this type of research, large data corpus are available (e.g. The literature has observed a growth in text sentiment analysis and image/video-based emotion recognition through body posture and facial expression. “computing that relates to, arises from, or influences emotions” 1, has gained prominence with more than 10k papers published between 2021–2023 (Scopus: searching for emotion and affective ( in the last 3 years). In recent years, the field of affective computing i.e. Our setup aims to be easily replicable in any real-life scenario, facilitating the collection of large datasets for novel affective computing systems. The data were collected in a group setting, which can give further context to emotion recognition systems. The dataset includes over 31 movie sessions, totaling 380 h+ of data from 190+ subjects. Emotion annotations were retrospectively performed on segments with elevated physiological responses. We collected physiological data (photoplethysmography and electrodermal activity) using a wrist-worn device during long-duration movie sessions. To address this, we present G-REx, a dataset for real-world affective computing. Emotion recognition with physiological data shows promising results in controlled experiments but lacks generalization to real-world settings. However, the incorporation of physiological data remains constrained. Affective computing has experienced substantial advancements in recognizing emotions through image and facial expression analysis.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |